Fine-Grained Self-Supervised Learning with Jigsaw puzzles for medical image classification.

Classifying fine-grained lesions is challenging due to minor and subtle differences in medical images. This is because learning features of fine-grained lesions with highly minor differences is very difficult in training deep neural networks. Therefore, in this paper, we introduce Fine-Grained Self-Supervised Learning(FG-SSL) method for classifying subtle lesions in medical images. The proposed method progressively learns the model through hierarchical block such that the cross-correlation between the fine-grained Jigsaw puzzle and regularized original images is close to the identity matrix. We also apply hierarchical block for progressive fine-grained learning, which extracts different information in each step, to supervised learning for discovering subtle differences. Our method does not require an asymmetric model, nor does a negative sampling strategy, and is not sensitive to batch size. We evaluate the proposed fine-grained self-supervised learning method on comprehensive experiments using various medical image recognition datasets. In our experiments, the proposed method performs favorably compared to existing state-of-the-art approaches on the widely-used ISIC2018, APTOS2019, and ISIC2017 datasets.

Reconstruction of retroauricolar surgical defect using the "jigsaw puzzle" advancement flap.

We present the case of a 55-year-old male patient who came to our attention because of a basal cell carcinoma of the right retroauricolar area, near the mastoid-auricle border. The tumor had a size of about 1.5 cm. Repairing retroauricolar surgical defects may be actually very challenging, firstly because an incorrect reconstruction may result in severe deformities which are extremely hard to conceal; so, we decided to employ the "jigsaw puzzle" advancement flap, a versatile flap, firstly successfully used in the reconstruction of a nasal ala defect.

Application of the Jigsaw Puzzle Flap Based on Freestyle Perforators to Repair Large and Deep Ulcers on the Buttocks.

Background: Decubitus ulcers are common skin injuries in plastic and burn surgery departments, usually occur in patients with a long disease course and poor underlying health. Designing a reconstruction procedure with safety blood supply to a large volume soft tissue and resulting in minimal trauma is a priority for surgeons. Methods: The free-style perforators on the potential donor sites surrounding the ulcers were detected by Doppler, and the area of the ulcer was divided into several sections based on the location of pre-design perforator flaps. According to the insertion point of the perforators, small V-Y advancement flaps, propeller flaps and rotation flaps pedicled with freestyle perforators were formed and moderately modified during surgery. All of the small flaps were transplanted from donor sites to the defect and reassembled into a new composite flap to repair the ulcer. The donor sites were directly closed. The area of the flaps ranged from 7.0 × 10.5 cm to 8.0 × 22.0 cm and the diameter of the pedicle perforators ranged from 0.5 to 4.0 mm. Results: In 30 patients, 65 flaps were constructed, and all of the flaps survived with direct closure of all donor sites. One case with effusion healed 1 month postoperatively through draining and application of a mild pressure dressing. After a 3-24 months follow-up period, all of the patients were satisfied with post-operative function and appearance, and only one case had a local recurrence 6 months postoperatively. Conclusion: The jigsaw puzzle flap based on freestyle perforators can repair the large skin and soft tissue defects caused by decubitus ulcers on the buttocks, with direct donor flap area closure. This method is easy to perform with a safe blood supply and minimal trauma resulting from the avoidance of microvascular anastomosis and the conventional myocutaneous flap.

Can the jigsaw puzzle model of protein folding re-assemble a hydrophobic core?

According to the "jigsaw puzzle" model of protein folding, the isomorphism between sequence and structure is substantially determined by the specific geometry of side-chain interactions, within the protein interior. In this work, we have attempted to predict the hydrophobic core of cyclophilin (LdCyp) from Leishmania donovani, utilizing a surface complementarity function, which selects for high goodness of fit between hydrophobic side-chain surfaces, rather in the manner of assembling a three-dimensional jigsaw puzzle. The computational core prediction method implemented here has been tried on two distinct scenarios, on the LdCyp polypeptide chain with native non-core residues and all core residues initially set to alanine, on a poly-glycine polypeptide chain. Molecular dynamics simulations appeared to indicate partial destabilization of the two designed sequences. However, experimental characterization of the designed sequences by circular dichroism (CD) spectroscopy and denaturant (GdmCl) induced unfolding, demonstrated disordered proteins. Stepwise reconstruction of the designed cores by cumulative sequential mutations identified the specific mutation (M122L) as primarily responsible for fold collapse and all design objectives were achieved upon rectifying this mutation. In summary, the study demonstrates regions of the core to contain highly specific (jigsaw puzzle-like) interactions sensitive to any perturbations and a predictive algorithm to identify such regions. A mutation within the core has been identified which exercises an inordinate influence on the global fold, reminiscent of metamorphic proteins. In addition, the computational procedure could predict substantial regions of the core (given main-chain coordinates) without any reference to non-core residues.

Facial microcystic adnexal carcinoma - treatment with a "jigsaw puzzle" advancement flap and immediate esthetic reconstruction: A case report.

BACKGROUND: Microcystic adnexal carcinoma (MAC) is a rare malignant tumor of the skin that is commonly found on the face. It grows slowly and has a low mortality rate. However, for various reasons, including strong histological invasiveness, clinical inexperience and inadequate procedure design, immediate or permanent facial deformity may occur after surgical operations. CASE SUMMARY: This article describes a middle-aged female artist who was diagnosed with MAC on the left upper lip. She declined the recommended treatment plan, which included two-stage reconstruction, skin grafting, or surgery that could have resulted in obvious facial dysfunction or esthetic deformity. We accurately designed a personalized procedure involving a "jigsaw puzzle advancement flap" for the patient based on the lesion location and the estimated area of skin loss. The procedure was successful; both pathological R0 resection and immediate and long-term esthetic reconstruction effects were achieved. CONCLUSION: This study suggests that when treating facial MAC or other skin malignancies, a surgical team should have sufficient plastic surgery-related knowledge and skills. An optimal surgical plan for an individual is needed to achieve good facial esthetics and functional recovery and shorten the treatment course.

A polymer-film inertial microfluidic sorter fabricated by jigsaw puzzle method for precise size-based cell separation.

A polymer-film inertial microfluidic jigsaw (PIMJ) sorter with trapezoidal spiral channels using the jigsaw puzzle method was proposed to realize precise and high-throughput rare cell separation. The PIMJ sorter was fabricated by assembling laser-patterned polymer-film layers of different thicknesses. After illustrating the conceptual design and fabrication process, the effects of the cross-sectional dimension, particle size, and operational flow rate on particle focusing were systematically explored under a broad flow rate range. Then, the separation performances of the PIMJ sorter were characterized using the binary particle mixture and the blood samples spiked with four types of tumor cells. The results indicated that the complete separation of the binary particles with a minimum size difference of 2 µm was successfully realized at a high throughput up to 3000 µL/min. A high recovery ratio of 90.57%-94.14% and a high purity of 48.67%-79.05% were achieved for the separation of rare tumor cells from white blood cells (WBCs). Finally, the PIMJ sorter was successfully employed for separating rare circulating tumor cells (CTCs) from the metastatic breast and lung cancer patients with a capture ratio of 7-226 CTCs per 5 mL sample. The results proved the high sensitivity and high reliability of the PIMJ sorter. The PIMJ sorter is expected to be a potential device for precise CTC separation towards the clinical applications.

Four-dimensional imaging with virtual reality to quantitatively explore jigsaw puzzle-like morphogenesis of Arabidopsis cotyledon pavement cells.

In most dicotyledonous plants, leaf pavement cells exhibit complex jigsaw puzzle-like cell morphogenesis during leaf expansion. Although detailed molecular biological information and mathematical modeling of this jigsaw puzzle-like cell morphogenesis are now available, a full understanding of this process remains elusive. Recent reports have highlighted the importance of three-dimensional (3D) structures (i.e., anticlinal and periclinal cell wall) in understanding the mechanical models that describe this morphogenetic process. We believe that it is important to acquire 3D shapes of pavement cells over time, i.e., acquire and analyze four-dimensional (4D) information when studying the relationship between mechanical modeling and simulations and the actual cell shape. In this report, we have developed a framework to capture and analyze 4D morphological information of Arabidopsis thaliana cotyledon pavement cells by using both direct water immersion observations and computational image analyses, including segmentation, surface modeling, virtual reality and morphometry. The 4D cell models allowed us to perform time-lapse 3D morphometrical analysis, providing detailed quantitative information about changes in cell growth rate and shape, with cellular complexity observed to increase during cell growth. The framework should enable analysis of various phenotypes (e.g., mutants) in greater detail, especially in the 3D deformation of the cotyledon surface, and evaluation of theoretical models that describe pavement cell morphogenesis using computational simulations. Additionally, our accurate and high-throughput acquisition of growing cell structures should be suitable for use in generating in silico model cell structures.

Effects of age and type of picture on visuospatial working memory assessed with a computerized jigsaw-puzzle task.

We investigated the effect of age and color in a computerized version of the jigsaw-puzzle task. In Experiment 1, young and older adults were presented with puzzles in color and black-and-white line drawings, varying in difficulty from 4 to 9 pieces. Older adults performed the task better with the black-and-white stimuli and younger adults performed better with the color ones. In Experiment 2, new older and young adults identified the same fragmented pictures as fast and accurately as possible. The older group identified the black-and-white stimuli faster than those presented in color, while the younger adults identified both similarly. In Experiment 3A, new older and young groups performed the puzzle task with the same color pictures and their monochrome versions. In Experiment 3B, participants performed a speeded identification task with the two sets. The findings of these experiments showed that older adults have a memory not a perceptual difficulty.

Robust Sex Differences in Jigsaw Puzzle Solving-Are Boys Really Better in Most Visuospatial Tasks?

Sex differences are consistently reported in different visuospatial tasks with men usually performing better in mental rotation tests while women are better on tests for memory of object locations. In the present study, we investigated sex differences in solving jigsaw puzzles in children. In total 22 boys and 24 girls were tested using custom build tablet application representing a jigsaw puzzle consisting of 25 pieces and featuring three different pictures. Girls outperformed boys in solving jigsaw puzzles regardless of the picture. Girls were faster than boys in solving the puzzle, made less incorrect moves with the pieces of the puzzle, and spent less time moving the pieces around the tablet. It appears that the strategy of solving the jigsaw puzzle was the main factor affecting differences in success, as girls tend to solve the puzzle more systematically while boys performed more trial and error attempts, thus having more incorrect moves with the puzzle pieces. Results of this study suggest a very robust sex difference in solving the jigsaw puzzle with girls outperforming boys by a large margin.

Shredded banknotes reconstruction using AKAZE points.

Shredded banknote reconstruction is a recent topic and can be viewed as solving large-scale jigsaw puzzles. Also, problems such as reconstruction of fragmented documents, photographs and historical artefacts are closely related with this topic. The high computational complexity of these problems increases the need for the development of new methods Reconstruction of shredded banknotes consists of three main stages. (1) Matching fragments with a reference banknote. (2) Aligning the fragments by rotating at certain angles. (3) Assembling the fragments. The existing methods can successfully applied to synthetic banknote fragments which are created in computer environment. But when real banknote reconstruction problem is considered, different sub problems arise and make the existing methods inadequate. In this study, a keypoint based method, named AKAZE, was used to make the matching process effective. This is the first study that uses the AKAZE method in the reconstruction of shredded banknotes. A new method for fragment alignment has also been proposed. In this method, the convex hulls that contain all true matched AKAZE keypoints were found on reference banknote and fragments. The orientations of fragments were estimated accurately by comparing these convex polygons. Also, a new criterion was developed to reveal the success rates of reconstructed banknotes. In addition, two different data sets including real and synthetic banknote fragments of different countries were created to test the success of proposed method.

Sequential Monte Carlo for Maximum Weight Subgraphs with Application to Solving Image Jigsaw Puzzles.

We consider a problem of finding maximum weight subgraphs (MWS) that satisfy hard constraints in a weighted graph. The constraints specify the graph nodes that must belong to the solution as well as mutual exclusions of graph nodes, i.e., pairs of nodes that cannot belong to the same solution. Our main contribution is a novel inference approach for solving this problem in a sequential monte carlo (SMC) sampling framework. Usually in an SMC framework there is a natural ordering of the states of the samples. The order typically depends on observations about the states or on the annealing setup used. In many applications (e.g., image jigsaw puzzle problems), all observations (e.g., puzzle pieces) are given at once and it is hard to define a natural ordering. Therefore, we relax the assumption of having ordered observations about states and propose a novel SMC algorithm for obtaining maximum a posteriori estimate of a high-dimensional posterior distribution. This is achieved by exploring different orders of states and selecting the most informative permutations in each step of the sampling. Our experimental results demonstrate that the proposed inference framework significantly outperforms loopy belief propagation in solving the image jigsaw puzzle problem. In particular, our inference quadruples the accuracy of the puzzle assembly compared to that of loopy belief propagation.