M.K. Bennett

Coventry University, Coventry, ENG, United Kingdom

Are you M.K. Bennett?

Claim your profile

Publications (20)61.98 Total impact

  • [show abstract] [hide abstract]
    ABSTRACT: Analysis of tissue is essential in dealing with a number of problems in cancer research. The identification of normal, dysplastic and cancerous colonic mucosa is an example of such a problem. In this paper, texture analysis techniques have been employed with the purpose of measuring characteristics of the tissue images. Those include histogram, grey-level difference statistics and co-occurrence matrix feature extraction algorithms. These characteristics are used as inputs for two different artificial intelligence approaches to address the image classification problem; a genetic algorithm and an artificial neural network. No significant differences have been found in the classifications obtained by both methodologies.
    Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE; 10/2003
  • [show abstract] [hide abstract]
    ABSTRACT: Patients with an intrathoracic oesophagogastrostomy after subtotal oesophagectomy experience profound duodenogastro-oesophageal reflux (DGOR). This study investigated the degree of mucosal injury and histopathological changes in oesophageal squamous epithelium after subtotal oesophagectomy with gastric interposition in relation to the extent of postoperative DGOR. Serial endoscopic assessment and systematic biopsy at the oesophagogastric anastomosis was undertaken in 40 patients following curative radical subtotal oesophagectomy and reconstruction with a gastric conduit subjected to a pyloroplasty. Thirty patients subsequently underwent combined 24-h ambulatory pH and bilirubin monitoring. Grade I-III oesophagitis was identified in 14 patients and oesophageal columnar epithelium in 19 patients. Biopsies from columnar regeneration revealed cardiac-type epithelium in ten patients and intestinal metaplasia in nine. Seven patients followed serially showed progression from cardiac-type epithelium to intestinal metaplasia. The incidence of Barrett's metaplasia was similar irrespective of the histological subtype of the resected tumour. Patients with oesophageal columnar epithelium had significantly higher acid (P = 0.015) and bilirubin (P = 0.011) reflux. Severe DGOR occurs following subtotal oesophagectomy and provides an environment for the acquisition of Barrett's metaplasia via a sequence of cardiac epithelium and eventual intestinal metaplasia.
    British Journal of Surgery 10/2003; 90(9):1120-8. · 4.84 Impact Factor
  • A J Sims, M K Bennett, A Murray
    [show abstract] [hide abstract]
    ABSTRACT: Pancreatic cancer is frequently associated with intense growth of fibrous tissue at the periphery of tumours, but the histopathological quantification of this stromal reaction has not yet been used as a prognostic factor because of the difficulty of obtaining quantitative measures using manual methods. Manual histological grading is a poor indicator of outcome in this type of cancer and there is a clinical need to establish a more sensitive indicator. Recent pancreatic tumour biology research has focused upon the stromal reaction and there is an indication that its histopathological quantification may lead to a new prognostic indicator. Histological samples from 21 cases of pancreatic carcinoma were stained using the sirius red, light-green method. Multiple images from the centre and periphery of each tumour were automatically segmented using colour cluster analysis to subdivide each image into representative colours. These were classified manually as stroma, cell cytoplasm or lumen in order to measure the area of each component in each image. Measured areas were analysed to determine whether the technique could detect spatial differences in the area of each tissue component over all samples, and within individual samples. Over all 21 cases, the area of stromal tissue at the periphery of the tumours exceeded that at the centre by an average of 10.0 percentage points (P < 0.001). Within individual tumours, the algorithm was able to detect significantly more stroma (P < 0.05) at the periphery than the centre in 11 cases, whilst none of the remaining cases had significantly more stromal tissue at the centre than the periphery. The results demonstrate that semi-automated analysis can be used to detect spatial differences in the area of fibrous tissue in routinely stained sections of pancreatic cancer.
    Physics in Medicine and Biology 07/2003; 48(13):N183-91. · 2.70 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: Analysis of tissue using image processing techniques is essential for dealing with a number of problems in cancer research. The identification of normal and cancerous colonic mucosa is such a problem. In this paper texture analysis techniques are used to measure certain characteristics of normal and cancerous tissue images. A genetic algorithm undertakes the analysis of those results in order to determine the operations useful for the given problem and in the most appropriate operation combination for the purpose of maximising the classification accuracy. The system developed for undertaking those tasks has been implemented on a cluster of Linux workstations using distributed computing techniques. A distributed programming message-passing library, PVM (Parallel Virtual Machine), provides the basis for building this system.
    Information Technology Applications in Biomedicine, 2003. 4th International IEEE EMBS Special Topic Conference on; 05/2003
  • [show abstract] [hide abstract]
    ABSTRACT: Background:Adenocarcinoma of the oesophagogastric junction (OGJ) is rapidly increasing in incidence and the role of radical lymphadenectomy for such tumours remains controversial. The aim of this study was to identify the pattern of metastatic nodal spread by histopathological assessment of all lymph node groups retrieved from resected specimens.Methods:Data were collected prospectively from patients undergoing potentially curative (R0) resection with lymphadenectomy for adenocarcinoma of the OGJ between January 1996 and May 1998. Patients with type 1 tumours (lower third of the oesophagus) underwent two-stage subtotal oesophagogastrectomy with two-tier lymphadenectomy. Patients with type 2 (gastric cardia) tumours underwent D2 total gastrectomy. At the time of surgery all lymph node groups were dissected out from the specimens, labelled and assessed by a single consultant histopathologist.Results:A total of 103 patients were studied. Eleven patients were understaged before operation and were inoperable or had palliative resections. Of the remaining 92 patients, 68 had type 1 tumours and 24 had type 2 tumours. Some 2301 nodes were analysed representing a median of 27 nodes per patient (26 from the oesophagectomy group and 30 from the gastrectomy group). Over 70 per cent of all patients had lymph node metastases at the time of surgery. Some 6 per cent of type 1 tumours with lymph node metastases had dissemination in both the abdominal and mediastinal nodal tiers. The common abdominal sites were the paracardial (right, 23 of 41; left, 23 of 41) and left gastric nodes (29 of 41) whereas within the mediastinum paraoesophageal (25 of 41) and bronchial (right, seven of 41; left, six of 41) metastases were more often encountered. Type 2 tumours had positive lymph nodes most frequently in the left paracardial (nine of 16), lesser curve (11 of 16) (N1 group) and left gastric (eight of 16) (N2 group) territories. The extent of lymph node positivity correlated with the T stage and differentiation of the primary tumour, as well as the presence of perineural, lymphatic and vascular invasion (P < 0·05).Conclusion:The high incidence and widespread dissemination of nodal metastases at the time of surgery seen with these tumours may justify the approach of systematic lymphadenectomy in the hope of performing a curative resection. The current definition of the lymph node sites in the abdominal and mediastinal tiers for type 1 tumours is based on experience with lower-third squamous carcinomas. These results demonstrate a different pattern of dissemination for junctional␣oesophageal adenocarcinomas requiring redefinition of the nodal stations to be resected in radical lymphadenectomies for such tumours. © 1999 British Journal of Surgery Society Ltd
    British Journal of Surgery 01/2003; 86(3):424 - 424. · 4.84 Impact Factor
  • Source
    A J Sims, M K Bennett, A Murray
    [show abstract] [hide abstract]
    ABSTRACT: Objective measurements of tissue area during histological examination of carcinoma can yield valuable prognostic information. However, such measurements are not made routinely because the current manual approach is time consuming and subject to large statistical sampling error. In this paper, a semi-automated image analysis method for measuring tissue area in histological samples is applied to the measurement of stromal tissue, cell cytoplasm and lumen in samples of pancreatic carcinoma and compared with the standard manual point counting method. Histological samples from 26 cases of pancreatic carcinoma were stained using the sirius red, light-green method. Images from each sample were captured using two magnifications. Image segmentation based on colour cluster analysis was used to subdivide each image into representative colours which were classified manually into one of three tissue components. Area measurements made using this technique were compared to corresponding manual measurements and used to establish the comparative accuracy of the semi-automated image analysis technique, with a quality assurance study to measure the repeatability of the new technique. For both magnifications and for each tissue component, the quality assurance study showed that the semi-automated image analysis algorithm had better repeatability than its manual equivalent. No significant bias was detected between the measurement techniques for any of the comparisons made using the 26 cases of pancreatic carcinoma. The ratio of manual to semi-automatic repeatability errors varied from 2.0 to 3.6. Point counting would need to be increased to be between 400 and 1400 points to achieve the same repeatability as for the semi-automated technique. The results demonstrate that semi-automated image analysis is suitable for measuring tissue fractions in histological samples prepared with coloured stains and is a practical alternative to manual point counting.
    Physics in Medicine and Biology 05/2002; 47(8):1255-66. · 2.70 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Knowledge of the pattern of recurrence of surgically treated cases of adenocarcinoma of the oesophago-gastric junction is important both for better understanding of their biological nature and for future strategic planning of therapy. The aim of this study is to demonstrate and compare the pattern of dissemination and recurrence in patients with Type I and Type II adenocarcinoma of oesophago-gastric junction. A prospective audit of the clinico-pathological features of patients who had undergone surgery with curative intent for adenocarcinoma of oesophago-gastric junction between 1991 and 1996 was undertaken. Patients were followed up by regular clinical examination. Clinical evaluation was supported by ultrasound, computerised tomography, radio-isotope bone scan, endoscopy and laparotomy each with biopsy and histology where appropriate. One hundred and sixty-nine patients with oesophago-gastric junction tumours (94 Type I and 75 Type II) have been followed up for a median of 75.3 (57-133) months. One hundred and three patients developed proven recurrent disease. The median time to recurrence was 23.3 (14.2-32.4) months for Type I and 20.5 (11.6-29.4) for Type II cancers. The most frequent type of recurrence was haematogenous (56% of Type I recurrences and 54% of Type II) of which 56% were detected within 1 year of surgery. The most frequent sites were to liver (27%), bone (18%) brain (11%) and lung (11%). Local recurrence occurred in 33% of Type I cancer and 29% of Type II recurrences. Nodal recurrence occurred in 18 and 25% of Type I and Type II cancer recurrences, most frequently to coeliac or porta hepatis nodes (64%). Only 7% of Type I and 15% of Type II cancer recurrences were by peritoneal dissemination. Type I and Type II adenocarcinoma of the oesophago-gastric junction have a predominantly early, haematogenous pattern of recurrence. There is a need to better identify the group of patients with small metastases at the time of diagnosis who are destined to develop recurrent disease in order that they may be spared surgery and those with micro metastases in order that they can be offered multi-modality therapy including early post operative or neo-adjuvant chemotherapy.
    British Journal of Cancer 05/2002; 86(8):1223-9. · 5.08 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: Analysis of tissue using image processing techniques is useful for dealing with a number of problems in cancer research. One such problem is the identification of normal, dysplastic and cancerous colonic mucosa. This research aims to identify the main image processing techniques necessary for this particular task, and to develop an automatic image classification system. Several texture analysis image-processing algorithms have been employed in this paper. Those can be separated into three categories, histogram features, grey-level difference statistics and co-occurrence matrix feature extraction algorithms. The classification system is implemented on a distributed system using PVM (Parallel Virtual Machine). PVM is a library for distributed application programming.
    [Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] EMBS/BMES Conference, 2002. Proceedings of the Second Joint; 02/2002
  • [show abstract] [hide abstract]
    ABSTRACT: Worldwide, colorectal cancer is the third most common malignant neoplasm. Automated classification of cytological images of colon tissue samples has been investigated, but diagnosis in all cases still requires human judgement. With the large numbers of cases of colon cancer each year, the workload placed on pathologists is immense. Texture is a powerful discriminating metric and the use of grey-level texture for classification of colon images has been extensively researched. One common technique is the extraction of texture metrics from grey-level co-occurrence matrices. However, using grey-scale images discards information contained in the differences of hue and saturation that may provide further classification information. We present the findings of an investigation of the discriminating ability of colour texture using co-occurrence matrices. Comparisons are made between grey-scale and colour texture analysis. Using statistical analysis, we show that classification using colour texture offers an improvement over classification based solely on grey-level texture.
    Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on; 02/2002
  • [show abstract] [hide abstract]
    ABSTRACT: Co-occurrence matrices are commonly used to extract fine texture information from images, and have been found to be a useful tool for measuring dysplasia in histological images of the colon. Pathologists, however, measure dysplasia in tissue samples at structural as well as cytological levels. We present our findings after investigating modifications to the cooccurrence matrix technique to measure this low frequency colour texture information for the classification of colon cancer images.
    Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society EMBS/BMES Conference, 2002. Proceedings of the Second Joint; 02/2002
  • [show abstract] [hide abstract]
    ABSTRACT: The incidence of adenocarcinoma of the esophagogastric junction is rapidly increasing, and the extent of lymphadenectomy for such tumors remains controversial. The aim of this study was to identify the pattern of dissemination by examination of all lymph nodes retrieved from resected tumors of the esophagogastric junction. The endoscopic and pathologic reports of patients who underwent RO resection for adenocarcinoma of the esophagogastric junction between January 1996 and November 1999 were examined. Patients with type 1 tumors (distal esophagus) underwent subtotal esophagectomy with 2-field lymphadenectomy. Patients with type 2 (gastric cardia) tumors underwent transhiatal D2 total gastro-esophagectomy. Lymph node groups were dissected from the main specimens and examined separately. One hundred and four type 1 and 48 type 2 tumors were studied. Median nodal recovery was 23 lymph nodes (type 1, 22 lymph nodes; type 2, 23 lymph nodes). Seventy-eight percent of the type 1 tumors with nodal metastases had dissemination in both the abdomen and mediastinum. The common abdominal sites were the paracardiac and the left gastric stations. Within the mediastinum, paraesophageal, paraaortic and tracheobronchial metastases were more often encountered. Type 2 tumors had positive lymph nodes most frequently in the left and right paracardiac, lesser curve (N1 group), and left gastric (N2 group) territories. Nodal status correlated with increasing depth of tumor invasion (P =.002). The pattern of nodal dissemination for cardia tumors concurs with that described by other studies. The current definition of nodal fields in the abdomen and mediastinum for esophageal tumors relates to experience with squamous carcinomas. Our results demonstrate a different pattern of dissemination for junctional esophageal adenocarcinomas. The nodal stations to be resected in radical lymphadenectomies for such tumors should be redefined.
    Surgery 02/2001; 129(1):103-9. · 3.37 Impact Factor
  • A.G. Todman, R.N.G. Naguib, M.K. Bennett
    [show abstract] [hide abstract]
    ABSTRACT: A number of quantitative techniques for the analysis of histopathological images used in the diagnosis of colonic cancer have been researched in the literature. While these methods have led to significant advances in the development of automated techniques, manual processing by a clinical expert remains the standard against which results are assessed. Here we explicitly attempt to build our understanding of human form perception, implemented at a neural level, into metrics that give us a measure of the extent to which the structure in an image displays a coherent orientational specificity. We describe the derivation of these metrics and consider their application to typical images of normal colon, dysplastic specimens, and moderately and poorly differentiated adenocarcinoma of colon. Preliminary results evaluating the effectiveness of the total activation ratio and the orthogonal activation ratio suggest that they are capable of separating images of normal colon tissue from those of moderately and poorly differentiated adenocarcinoma of colon
    Electrical and Computer Engineering, 2001. Canadian Conference on; 02/2001
  • [show abstract] [hide abstract]
    ABSTRACT: Argon plasma coagulation is a diathermy-based non-contact therapeutic endoscopic modality that may have a lower risk of perforation than other tissue ablation techniques. Its effect was studied on three fresh esophageal and three fresh gastric resection specimens using power settings from 40 to 99 Watts at 90 degrees, with 1 mm separation using pulse durations of 1 and 3 seconds. A scoring system for depth of tissue damage was created and samples were analyzed blindly by a gastrointestinal histopathologist. There was significantly greater damage to gastric tissue using a 3-second (compared with 1-second) pulse (p = 0.003) and marginally significantly greater damage to esophageal tissue using the 3-second pulse (p = 0.053). Tissue damage was related to power setting for gastric (p = 0.031) but not for esophageal tissue (p = 0. 065). Only 1 of 42 esophageal samples and 2 of 42 gastric samples examined showed damage extending into the muscularis propria. Deep tissue damage that could lead to perforation was rare with argon plasma coagulation. The depth of gastric mucosal damage increased with increased pulse duration and increasing power settings, and, although the depth of esophageal mucosal damage was marginally related to pulse duration, it was not related to the power setting. (Gastrointest Endosc 2000;52:342-5).
    Gastrointestinal Endoscopy 10/2000; 52(3):342-5. · 5.21 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: Image analysis for the classification of normal and cancerous colonic mucosa is reported. Pathology samples were taken from human colon mucosa, and 44 normal and 58 cancer images captured to computer via an optical microscope with a CCD camera. Texture analysis was performed using fractal dimension, entropy and correlation. Using non-parametric classification, fractal dimension improved the classification accuracy from 88% to 94% in comparison with the combined entropy and correlation analysis
    Image Processing And Its Applications, 1999. Seventh International Conference on (Conf. Publ. No. 465); 08/1999
  • [show abstract] [hide abstract]
    ABSTRACT: The development of an automated algorithm for the categorization of normal and cancerous colon mucosa is reported. Six features based on texture analysis were studied. They were derived using the co-occurrence matrix and were angular second moment, entropy, contrast, inverse difference moment, dissimilarity, and correlation. Optical density was also studied. Forty-four normal images and 58 cancerous images from sections of the colon were analyzed. These two groups were split equally into two subgroups: one set was used for supervised training and the other to test the classification algorithm. A stepwise selection procedure showed that correlation and entropy were the features that discriminated most strongly between normal and cancerous tissue (P<0.0001). A parametric linear-discriminate function was used to determine the classification rule. For the training set, a sensitivity and specificity of 93.1% and 81.8%, respectively, were achieved, with an overall accuracy of 88.2%. These results mere confirmed with the test set, with a sensitivity and specificity of 93.1% and 86.4%, respectively, and an overall accuracy of 90.2%.
    IEEE Transactions on Information Technology in Biomedicine 10/1998; · 1.98 Impact Factor
  • A N Esgiar, R N Naguib, M K Bennett, A Murray
    [show abstract] [hide abstract]
    ABSTRACT: To assess an automated algorithm, developed for the classification of normal and cancerous colonic mucosa, using geometric analysis of features and texture analysis. Twenty-one images were analyzed, 10 from normal and 11 from cancerous mucosa. The classification was based on a regularity index dependent on shape, object orientation for establishing parallelism and five texture features derived using the co-occurrence image analysis method. Geometric analysis yielded an overall classification accuracy of 80%. The corresponding sensitivity and specificity were 94% and 64%, respectively. Using texture analysis, the overall classification accuracy was 90%, with a sensitivity and specificity of 82% and 100%, respectively. This initial study demonstrated that geometric and texture analysis techniques show promise for automated analysis of colon cancer.
    Analytical and quantitative cytology and histology / the International Academy of Cytology [and] American Society of Cytology 09/1998; 20(4):297-301. · 0.60 Impact Factor
  • Source
    A Murray, V Allen, M K Bennett
    [show abstract] [hide abstract]
    ABSTRACT: To develop a technique for automatic inflation of a percutaneous transluminal coronary angioplasty (PTCA) balloon, with continuous measurement of the balloon pressure and volume; to validate the technique for determining the mechanical characteristics of coronary arteries. During necropsy examination of the hearts of nine patients, 17 coronary artery samples were obtained for histological examination. A PTCA balloon was inserted into each artery, and the balloon pressure and volume were measured continuously during four repeat automatic inflations of the balloon. Of the 17 arteries, eight showed elastic, six plastic, and three fracture pressure-volume deformation characteristics. For the plastic deformations, the first inflation required a higher pressure than subsequent repeat inflations of 82 (61) kPa (mean (SD), range 25 to 175 kPa). For the three in the fracture group, the pressure drop because of the fracture occurred between 210 and 540 kPa. Two of these three showed a tear on visual inspection, and the other showed disruption of the intimal plaque on blinded histological examination. Of the six with plastic deformation characteristics alone, one showed a tear, and on histological examination two others showed splitting of the internal and external elastic lamina and one showed separation of intima and media. None in the elastic group showed any of these characteristics. Plastic and fracture deformation characteristics could be differentiated from elastic characteristics. Visual or histological evidence of fracturing was present in all three arteries identified during angioplasty as having pressure-volume fracture characteristics.
    Heart (British Cardiac Society) 07/1998; 79(6):608-12. · 5.01 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: Pre-operative data from 103 patients undergoing potentially curative resection of adenocarcinoma of the oesophago-gastric junction were collected prospectively and analysed by a radial basis function artificial neural network system. A separate neural structure was designed for use with selected additional post-operative parameters. Output variables for both systems were recurrence at 12, 18 and 24 months. Prediction specificities, using pre-operative data alone, were 60%, 62% and 60%, respectively. Inclusion of post-operative parameters improved the specificity to 72.7% at 12 months, 66% at 18 months and 62.2% at 24 months, while the sensitivity of prediction at 18 months reached 90% and at two years 93%. There was a strong correlation between the predictive value of pre- and post-operative findings in individual patients at each time period (correlation coefficient=0.6333, p
    01/1998; 6.
  • Gastroenterology 01/1998; 114. · 12.82 Impact Factor
  • Gastroenterology 01/1998; 114. · 12.82 Impact Factor

Publication Stats

322 Citations
61.98 Total Impact Points


  • 2001–2003
    • Coventry University
      • Faculty of Engineering and Computing
      Coventry, ENG, United Kingdom
  • 1998–2003
    • The Newcastle upon Tyne Hospitals NHS Foundation Trust
      • Department of Cardiology
      Newcastle upon Tyne, ENG, United Kingdom
  • 1998–2002
    • Newcastle University
      • School of Electrical and Electronic Engineering
      Newcastle-on-Tyne, England, United Kingdom