Intraoperative margin assessment of human breast tissue in optical coherence tomography images using deep neural networks.

Assessing the surgical margin during breast lumpectomy operations can avoid the need for additional surgery. Optical coherence tomography (OCT) is an imaging technique that has been proven to be efficient for this purpose. However, to avoid overloading the surgeon during the operation, automatic cancer detection at the surface of the removed tissue is needed. This work explores automated margin assessment on a sample of patient data collected at the Pathology Department, Severance Hospital (Seoul, South Korea). Some methods based on the spatial statistics of the images have been developed, but the obtained results are still far from human performance. In this work, we investigate the possibility to use deep neural networks (DNNs) for real time margin assessment, demonstrating performance significantly better than the reported literature and close to the level of a human expert. Since the goal is to detect the presence of cancer, a patch-based classification method is proposed, as it is sufficient for detection, and requires training data that is easier and cheaper to collect than for other approaches such as segmentation. For that purpose, we train a DNN architecture that was proved to be efficient for small images on patches extracted from images containing only cancer or only normal tissue as determined by pathologists in a university hospital. As the number of available images in all such studies is by necessity small relative to other deep network applications such as ImageNet, a good regularization method is needed. In this work, we propose to use a recently introduced function norm regularization that attempts to directly control the function complexity, in contrast to classical approaches such as weight decay and DropOut. As neither the code nor the data of previous results are publicly available, the obtained results are compared with reported results in the literature for a conservative comparison. Moreover, our method is applied to locally collected data on several data configurations. The reported results are the average over the different trials. The experimental results show that the use of DNNs yields significantly better results than other techniques when evaluated in terms of sensitivity, specificity, F1 score, G-mean and Matthews correlation coefficient. Function norm regularization yielded higher and more robust results than competing regularization methods. We have demonstrated a system that shows high promise for (partially) automated margin assessment of human breast tissue, Equal error rate (EER) is reduced from approximately 12% (the lowest reported in the literature) to 5% - a 58% reduction. The method is computationally feasible for intraoperative application (less than 2 s per image) at the only cost of a longer offline training time.

Impedance imaging with first-order TV regularization.

EIT problem is a typical inverse problem with serious ill-posedness. In general, regularization techniques are necessary for such ill-posed inverse problems. To overcome ill-posedness, the total variation (TV) regularization is widely used and it is also successfully applied to EIT. For realtime monitoring, a fast and robust image reconstruction algorithm is required. By exploiting recent advances in optimization, we propose a first-order TV algorithm for EIT, which simply consists of matrix-vector multiplications and in which the sparse structure of the system can be easily exploited. Furthermore, a typical smoothing parameter to overcome nondifferentibility of the TV term is not needed and a closed form solution can be applied in part using soft thresholding. It shows a fast reconstruction in the beginning. Numerical experiments using simulated data and real experimental data support our claim.

Environmentally robust motion detection for video surveillance.

Most video surveillance systems require to manually set a motion detection sensitivity level to generate motion alarms. The performance of motion detection algorithms, embedded in closed circuit television (CCTV) camera and digital video recorder (DVR), usually depends upon the preselected motion sensitivity level, which is expected to work in all environmental conditions. Due to the preselected sensitivity level, false alarms and detection failures usually exist in video surveillance systems. The proposed motion detection model based upon variational energy provides a robust detection method at various illumination changes and noise levels of image sequences without tuning any parameter manually. We analyze the structure mathematically and demonstrate the effectiveness of the proposed model with numerous experiments in various environmental conditions. Due to the compact structure and efficiency of the proposed model, it could be implemented in a small embedded system.

A Case of Salvage Operation in Radiation-Failed Squamous Cell Carcinoma Transformed from Bowen's Disease / 대한이비인후과학회지

Bowen's disease was first described by Bowen in 1912 as a precancerous dermatosis. It is believed that its main causes are exposure to UV and a history of arsenic ingestion. Bowen's disease are precursor lesions, 5 percent of which is believed to develop into squamous cell carcinoma. It is stated in the literature that those patients in whom invasive cell carcinoma develops, 13 per cent of the lesions metastasize and death eventually occurs in 10 per cent of them. Therefore, elective lymphadenectomy is rarely indicated and is usually reserved for recurrent, histologically aggressive, deeply invasive and large (greater than 2 cm) tumors. Deeply invasive tumors of the preauricular and mandibular area frequently require parotidectomy to provide an adequate deep margin, to remove the primary echelon lymph nodes and to protect the facial nerve. We report a case of salvage operation on squamous cell carcinoma that had transformed from Bowen's disease.