A First Step Towards an Algorithm for Breast Cancer Reoperation Prediction Using Machine Learning and Mammographic Images
(2022) In Master's Theses in Mathematical Sciences FMAM05 20221Mathematics (Faculty of Engineering)
- Abstract
- Cancer is the second leading cause of death worldwide and 30% of all cancer cases among women are breast cancer. A popular treatment is breast-conserving surgery, where only a part of the breast is surgically removed. Surgery is expensive and has a significant impact on the body, and on some women, a reoperation is needed. The aim of this thesis was to see if there is a possibility to predict whether a person will be in need of reoperation with the help of whole mammographic images and deep learning. \\
The data used in this thesis were collected from two different open sources: (1) The Chinese Mammography Database (CMMD) where 1052 benign images and 1090 malignant images were used. (2) The Curated Breast Imaging Subset of Digital... (More) - Cancer is the second leading cause of death worldwide and 30% of all cancer cases among women are breast cancer. A popular treatment is breast-conserving surgery, where only a part of the breast is surgically removed. Surgery is expensive and has a significant impact on the body, and on some women, a reoperation is needed. The aim of this thesis was to see if there is a possibility to predict whether a person will be in need of reoperation with the help of whole mammographic images and deep learning. \\
The data used in this thesis were collected from two different open sources: (1) The Chinese Mammography Database (CMMD) where 1052 benign images and 1090 malignant images were used. (2) The Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) where 182 benign images and 145 malignant images were used. With those images, both a simple convolutional neural network (CNN) and a transfer learning network using the pre-trained model MobileNet were trained to classify the images as benign or malignant. All the networks were evaluated using learning curves, confusion matrix, accuracy, sensitivity, specificity, AUC and a ROC-curve.
The highest results obtained belonged to a transfer learning network that used the pre-trained model MobileNet and trained on the CMMD data set. It got an AUC value of 0.599. (Less) - Abstract (Swedish)
- Cancer är idag det näst vanligaste dödsorsaken i världen, där 30% av alla cancerfall bland kvinnor är bröstcancer. En vanlig behandling är bröstbevarande operation, där en bit av bröstet kirurgiskt tas bort. Operationer är både dyrt och har en betydande inverkan på kroppen och för vissa kvinnor krävs en omoperation efter den första operationen. Syftet med detta arbete har varit att undersöka möjligheten att förutsäga om en person kommer att vara i behov av en omoperation med hjälp av hela mammografibilder och maskininlärning.
Datan som användes i arbetet hämtades från två olika öppna källor: (1) The Chinese Mammography Database (CMMD) där 1052 benigna bilder och 1090 maligna bilder användes. (2) The Curated Breast Imaging Subset of... (More) - Cancer är idag det näst vanligaste dödsorsaken i världen, där 30% av alla cancerfall bland kvinnor är bröstcancer. En vanlig behandling är bröstbevarande operation, där en bit av bröstet kirurgiskt tas bort. Operationer är både dyrt och har en betydande inverkan på kroppen och för vissa kvinnor krävs en omoperation efter den första operationen. Syftet med detta arbete har varit att undersöka möjligheten att förutsäga om en person kommer att vara i behov av en omoperation med hjälp av hela mammografibilder och maskininlärning.
Datan som användes i arbetet hämtades från två olika öppna källor: (1) The Chinese Mammography Database (CMMD) där 1052 benigna bilder och 1090 maligna bilder användes. (2) The Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) får 182 benigna bilder och 145 maligna bilder användes. Med dessa bilder tränades både ett enkelt konvoluionellt nätverk och ett överförningsinlärningsnätverk med den för-tränade modellen MobileNet för att klassificera bilderna som benigna eller maligna. Alla nätverken utvärderades med inlärningskurvor, confusion matrix, noggrannhet, känslighet, specificitet och en ROC-kurva.
De högsta resultaten som erhölls var ett AUC-värde på 0.599 och tillhörde ett överföringsinlärning nätverk som använt den för-tränade modellen MobileNet och tränat på CMMD-datauppsättningen. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9088610
- author
- Jönsson, Emma LU
- supervisor
-
- Ida Arvidsson LU
- Jennie Karlsson LU
- organization
- course
- FMAM05 20221
- year
- 2022
- type
- H2 - Master's Degree (Two Years)
- subject
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3475-2022
- ISSN
- 1404-6342
- other publication id
- 2022:E26
- language
- English
- id
- 9088610
- date added to LUP
- 2022-08-10 18:38:51
- date last changed
- 2022-08-10 18:38:51
@misc{9088610, abstract = {{Cancer is the second leading cause of death worldwide and 30% of all cancer cases among women are breast cancer. A popular treatment is breast-conserving surgery, where only a part of the breast is surgically removed. Surgery is expensive and has a significant impact on the body, and on some women, a reoperation is needed. The aim of this thesis was to see if there is a possibility to predict whether a person will be in need of reoperation with the help of whole mammographic images and deep learning. \\ The data used in this thesis were collected from two different open sources: (1) The Chinese Mammography Database (CMMD) where 1052 benign images and 1090 malignant images were used. (2) The Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) where 182 benign images and 145 malignant images were used. With those images, both a simple convolutional neural network (CNN) and a transfer learning network using the pre-trained model MobileNet were trained to classify the images as benign or malignant. All the networks were evaluated using learning curves, confusion matrix, accuracy, sensitivity, specificity, AUC and a ROC-curve. The highest results obtained belonged to a transfer learning network that used the pre-trained model MobileNet and trained on the CMMD data set. It got an AUC value of 0.599.}}, author = {{Jönsson, Emma}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{A First Step Towards an Algorithm for Breast Cancer Reoperation Prediction Using Machine Learning and Mammographic Images}}, year = {{2022}}, }