ABSTRACT
Objectives@#Breast cancer is the most common cancer diagnosed in women, and microcalcification (MCC) clusters act as an early indicator. Thus, the detection of MCCs plays an important role in diagnosing breast cancer. @*Methods@#This paper presents a methodology for mammogram preprocessing and MCC detection. The preprocessing method employs automatic artefact deletion and pectoral muscle removal based on region-growing segmentation and polynomial contour fitting. The MCC detection method uses a convolutional neural network for region-of-interest (ROI) classification, along with morphological operations and wavelet reconstruction to reduce false positives (FPs). @*Results@#The methodology was evaluated using the mini-MIAS and UTP datasets in terms of segmentation accuracy in the preprocessing phase, as well as sensitivity and the mean FP rate per image in the MCC detection phase. With the mini-MIAS dataset, the proposed methods achieved accuracy scores of 99% for breast segmentation and 95% for pectoral segmentation, a sensitivity score of 82% for MCC detection, and an FP rate per image of 3.27. With the UTP dataset, the methods achieved accuracy scores of 97% for breast segmentation and 91% for pectoral segmentation, a sensitivity score of 78% for MCC detection, and an FP rate per image of 0.74. @*Conclusions@#The proposed preprocessing method outperformed the state-of-the-art methods for breast segmentation and achieved relatively good results for pectoral muscle removal. Furthermore, the MCC detection module achieved the highest test accuracy in identifying potential ROIs with MCCs compared to other methods.
ABSTRACT
Objectives@#Breast cancer is the most common cancer diagnosed in women, and microcalcification (MCC) clusters act as an early indicator. Thus, the detection of MCCs plays an important role in diagnosing breast cancer. @*Methods@#This paper presents a methodology for mammogram preprocessing and MCC detection. The preprocessing method employs automatic artefact deletion and pectoral muscle removal based on region-growing segmentation and polynomial contour fitting. The MCC detection method uses a convolutional neural network for region-of-interest (ROI) classification, along with morphological operations and wavelet reconstruction to reduce false positives (FPs). @*Results@#The methodology was evaluated using the mini-MIAS and UTP datasets in terms of segmentation accuracy in the preprocessing phase, as well as sensitivity and the mean FP rate per image in the MCC detection phase. With the mini-MIAS dataset, the proposed methods achieved accuracy scores of 99% for breast segmentation and 95% for pectoral segmentation, a sensitivity score of 82% for MCC detection, and an FP rate per image of 3.27. With the UTP dataset, the methods achieved accuracy scores of 97% for breast segmentation and 91% for pectoral segmentation, a sensitivity score of 78% for MCC detection, and an FP rate per image of 0.74. @*Conclusions@#The proposed preprocessing method outperformed the state-of-the-art methods for breast segmentation and achieved relatively good results for pectoral muscle removal. Furthermore, the MCC detection module achieved the highest test accuracy in identifying potential ROIs with MCCs compared to other methods.
ABSTRACT
Background@#Untreated osteonecrosis of the femoral head ultimately leads to secondary coxarthrosis. The aim of this study was to determinate if the core decompression of the femoral head combined with implantation of autologous bone marrow concentrate with tricalcium phosphate could be used to prevent radiographic progression of early stage osteonecrosis of the hip. We also sought to determine whether this treatment improved clinical outcomes and reduced the need for total hip arthroplasty. @*Methods@#Eighteen hips were included in the present study. All of them underwent core decompression of the femoral head combined with implantation of autologous bone marrow concentrate with tricalcium phosphate between 2007 and 2012. The cell concentrate was obtained from the posterior iliac crest and processed and implanted during the same surgical procedure. Patient demographic data, clinical data including modified Harris hip score, and radiological data were collected preoperatively, postoperatively, and during the follow-up period. Also, survival endpoints were analyzed: time of femoral head collapse and need for total hip arthroplasty. @*Results@#The mean age of patients was 37.8 years (standard deviation [SD], 9.31 years). The mean follow-up was 68.9 months (SD, 15.0 months). In most cases (70.6%), the etiology of the osteonecrosis of the femoral head was corticosteroid use; in the remaining cases, secondary to alcohol use. Core decompression of the femoral head combined with implantation of autologous bone marrow concentrate with tricalcium phosphate did not prevent progression to collapse (< 80% at 5 years) although modified Harris hip scores improved. Overall median survival with the total hip arthroplasty as endpoint was 23 months (95% confidence interval [CI], 14.9 to 31.1 months). Overall median survival time with any degree of collapse as endpoint was 7 months (95% CI, 2.0 to 12.0 months). @*Conclusions@#The results obtained in this study suggest that core decompression combined with implantation of autologous bone marrow concentrate and tricalcium phosphate will not prevent radiographic progression of early stage osteonecrosis of the hip. These finding also suggest that the absence of indications for hip replacement alone is not an indicator of good response to the treatment, and it is important to note the radiological results.
ABSTRACT
Ischiofemoral impingement syndrome is a rare clinical entity characterized by chronic groin, buttock or hip pain associated with radiographic evidence of narrowing of the space between the lesser femoral trochanter and the ischial tuberosity. Introduction of magnetic resonance imaging to the clinical practice as well as the establishment of the radiological definition of the abnormal ischiofemoral distance has led to an increasing interest in this condition. Ischiofemoral impingement syndrome is a poorly understood disorder of chronic pain, especially regarding its treatment. The authors present two cases of primary ischiofemoral impingement syndrome successfully treated with a minimally invasive surgical technique. With this endoscopic technique, it was possible to resect the lesser trochanter and restore the ischiofemoral space. Immediate clinical and functional improvement was reported by both patients.